Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Alzheimer's Magnetic Resonance Imaging Classification Using Deep and Meta-Learning Models

Nida Nasir, Muneeb Ahmed, Neda Afreen, Mustafa Sameer

TL;DR

Diagnosing Alzheimer's disease from MRI remains challenging due to data complexity. The paper evaluates five pretrained CNNs (ResNet-18, Inception V3, SqueezeNet V1, MobileNet V1, VGG-11 BN) on entropy-selected MRI frames from the ADNI dataset and compares ensemble methods, finding that a 50-best-entropy-frame subset plus majority voting yields the best performance. The proposed approach achieves about 90% test accuracy with recall near 0.89, and the majority vote ensemble reduces prediction variance relative to stacking. The work demonstrates the value of entropy-based data reduction and simple ensemble strategies for reliable AD detection, with future scope for multimodal data and broader clinical deployment.

Abstract

Deep learning, a cutting-edge machine learning approach, outperforms traditional machine learning in identifying intricate structures in complex high-dimensional data, particularly in the domain of healthcare. This study focuses on classifying Magnetic Resonance Imaging (MRI) data for Alzheimer's disease (AD) by leveraging deep learning techniques characterized by state-of-the-art CNNs. Brain imaging techniques such as MRI have enabled the measurement of pathophysiological brain changes related to Alzheimer's disease. Alzheimer's disease is the leading cause of dementia in the elderly, and it is an irreversible brain illness that causes gradual cognitive function disorder. In this paper, we train some benchmark deep models individually for the approach of the solution and later use an ensembling approach to combine the effect of multiple CNNs towards the observation of higher recall and accuracy. Here, the model's effectiveness is evaluated using various methods, including stacking, majority voting, and the combination of models with high recall values. The majority voting performs better than the alternative modelling approach as the majority voting approach typically reduces the variance in the predictions. We report a test accuracy of 90% with a precision score of 0.90 and a recall score of 0.89 in our proposed approach. In future, this study can be extended to incorporate other types of medical data, including signals, images, and other data. The same or alternative datasets can be used with additional classifiers, neural networks, and AI techniques to enhance Alzheimer's detection.

Alzheimer's Magnetic Resonance Imaging Classification Using Deep and Meta-Learning Models

TL;DR

Diagnosing Alzheimer's disease from MRI remains challenging due to data complexity. The paper evaluates five pretrained CNNs (ResNet-18, Inception V3, SqueezeNet V1, MobileNet V1, VGG-11 BN) on entropy-selected MRI frames from the ADNI dataset and compares ensemble methods, finding that a 50-best-entropy-frame subset plus majority voting yields the best performance. The proposed approach achieves about 90% test accuracy with recall near 0.89, and the majority vote ensemble reduces prediction variance relative to stacking. The work demonstrates the value of entropy-based data reduction and simple ensemble strategies for reliable AD detection, with future scope for multimodal data and broader clinical deployment.

Abstract

Deep learning, a cutting-edge machine learning approach, outperforms traditional machine learning in identifying intricate structures in complex high-dimensional data, particularly in the domain of healthcare. This study focuses on classifying Magnetic Resonance Imaging (MRI) data for Alzheimer's disease (AD) by leveraging deep learning techniques characterized by state-of-the-art CNNs. Brain imaging techniques such as MRI have enabled the measurement of pathophysiological brain changes related to Alzheimer's disease. Alzheimer's disease is the leading cause of dementia in the elderly, and it is an irreversible brain illness that causes gradual cognitive function disorder. In this paper, we train some benchmark deep models individually for the approach of the solution and later use an ensembling approach to combine the effect of multiple CNNs towards the observation of higher recall and accuracy. Here, the model's effectiveness is evaluated using various methods, including stacking, majority voting, and the combination of models with high recall values. The majority voting performs better than the alternative modelling approach as the majority voting approach typically reduces the variance in the predictions. We report a test accuracy of 90% with a precision score of 0.90 and a recall score of 0.89 in our proposed approach. In future, this study can be extended to incorporate other types of medical data, including signals, images, and other data. The same or alternative datasets can be used with additional classifiers, neural networks, and AI techniques to enhance Alzheimer's detection.
Paper Structure (24 sections, 5 equations, 5 figures, 4 tables)

This paper contains 24 sections, 5 equations, 5 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Literature review
  3. Methodology
  4. Dataset
  5. Preprocessing
  6. Deep Learning Models
  7. RESNET 18
  8. INCEPTION V3
  9. Squeezenet V1
  10. Mobilenet V1
  11. VGG 11 (BN)
  12. Ensemble Stacking
  13. majority voting ensemble
  14. Results
  15. Experimental Setup
  16. ...and 9 more sections

Figures (5)

  • Figure 1: Workflow of the proposed system.
  • Figure 2: Sample population of Brain MRI Scans from ADNI dataset.
  • Figure 3: Illustrated Confusion Matrices of test data evaluated on different models (row wise) and sample sizes (column wise).
  • Figure 4: ROC curves for majority voting algorithm on MobilenetV2, VGG11 (BN) and SqueezenetV1 across different classes (OneVsAll).
  • Figure 5: Ensemble Stacking and Majority Voting.